© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 18-RES-MATRYOSHKA-DC
    7. 1393
    Prev
    Next
    INDEX
    Explanations

    words related to identifying categories or making distinctions

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.18.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
    setof
    -0.56
    another
    -0.56
    jzen
    -0.50
    nuff
    -0.50
     almeno
    -0.48
     آخر
    -0.47
     kasarigan
    -0.47
    なんか
    -0.47
     weiteres
    -0.47
     unhappiness
    -0.46
    POSITIVE LOGITS
     either
    0.96
    owohl
    0.95
     both
    0.90
     einerseits
    0.89
    ArgsConstructor
    0.88
    either
    0.84
    agisse
    0.83
     whether
    0.80
    fjspx
    0.78
    tagHelperRunner
    0.77
    Activations Density 2.616%

    No Known Activations